Hasil untuk "Academies and learned societies"

Celeste Veronese, Daniele Meli, Alessandro Farinelli

This paper presents a novel approach combining inductive logic programming with reinforcement learning to improve training performance and explainability. We exploit inductive learning of answer set programs from noisy examples to learn a set of logical rules representing an explainable approximation of the agent policy at each batch of experience. We then perform answer set reasoning on the learned rules to guide the exploration of the learning agent at the next batch, without requiring inefficient reward shaping and preserving optimality with soft bias. The entire procedure is conducted during the online execution of the reinforcement learning algorithm. We preliminarily validate the efficacy of our approach by integrating it into the Q-learning algorithm for the Pac-Man scenario in two maps of increasing complexity. Our methodology produces a significant boost in the discounted return achieved by the agent, even in the first batches of training. Moreover, inductive learning does not compromise the computational time required by Q-learning and learned rules quickly converge to an explanation of the agent policy.

Jihan Avie Yusrina, Nujumun Niswah, Rubai Rubai

This research is motivated by the stagnation of Indonesia's gender equality index score, which ranks 87 out of 146 countries, the strong influence of patriarchal values, and the high rate of gender-based violence. This condition demands a more practical approach to promoting gender equality, primarily through inclusive education from an early age. The golok-golok menthok tradition in Kudus, Central Java, was chosen as the object of study because it has great potential to integrate gender equality values into people's daily lives. The purpose of this study is to explore how the golok-golok menthok tradition can be a medium for gender-inclusive education that promotes values of justice. The method used is a descriptive qualitative approach. The results show that the golok-golok menthok tradition not only functions as a religious celebration but also as a tool to transmit gender equality values to the younger generation. This tradition emphasizes that gender justice is part of a complete faith and must be integrated into daily life. The implications of this research show that culture and religion can synergize in promoting gender equality, forming a strong foundation for future generations to be fair and respectful of gender differences. Keywords: Gender Equality, Golok-golok Menthok, Islam; Local Tradition

Jonathan Sillito, Matt Pope

Due to various sources of uncertainty, emergent behavior, and ongoing changes, the reliability of many socio-technical systems depends on an iterative and collaborative process in which organizations (1) analyze and learn from system failures, and then (2) co-evolve both the technical and human parts of their systems based on what they learn. Many organizations have defined processes for learning from failure, often involving postmortem analyses conducted after any system failures that are judged to be sufficiently severe. Despite established processes and tool support, our preliminary research, and professional experience, suggest that it is not straightforward to take what was learned from a failure and successfully improve the reliability of the socio-technical system. To better understand this collaborative process and the associated challenges, we are conducting a study of how teams learn from failure. We are gathering incident reports from multiple organizations and conducting interviews with engineers and managers with relevant experience. Our analytic interest is in what is learned by teams as they reflect on failures, the learning processes involved, and how they use what is learned. Our data collection and analysis are not yet complete, but we have so far analyzed 13 incident reports and seven interviews. In this short paper we (1) present our preliminary findings, and (2) outline our broader research plans.

Hamilton Almeida

O rádio, a mídia de maior penetração no planeta, nasceu de maneira surpreendente: em um país periférico, distante dos grandes centros de ciência. A façanha foi realizada por um padre católico brasileiro que trabalhava sozinho e dispunha de poucos recursos. No final do século XIX, Roberto Landell de Moura foi protagonista de pelo menos duas das mais antigas transmissões de voz por ondas de rádio da história. Lutando contra tudo e contra todos – destruíram os seus aparelhos porque era “um padre que falava com o demônio” - patenteou os seus inventos no Brasil e nos EUA. Mesmo assim, não recebeu nenhum apoio financeiro. É mais um exemplo do conflito secular entre o negacionismo e a ciência.

Depeng Li, Zhigang Zeng

In the scenario of class-incremental learning (CIL), deep neural networks have to adapt their model parameters to non-stationary data distributions, e.g., the emergence of new classes over time. However, CIL models are challenged by the well-known catastrophic forgetting phenomenon. Typical methods such as rehearsal-based ones rely on storing exemplars of old classes to mitigate catastrophic forgetting, which limits real-world applications considering memory resources and privacy issues. In this paper, we propose a novel rehearsal-free CIL approach that learns continually via the synergy between two Complementary Learning Subnetworks. Our approach involves jointly optimizing a plastic CNN feature extractor and an analytical feed-forward classifier. The inaccessibility of historical data is tackled by holistically controlling the parameters of a well-trained model, ensuring that the decision boundary learned fits new classes while retaining recognition of previously learned classes. Specifically, the trainable CNN feature extractor provides task-dependent knowledge separately without interference; and the final classifier integrates task-specific knowledge incrementally for decision-making without forgetting. In each CIL session, it accommodates new tasks by attaching a tiny set of declarative parameters to its backbone, in which only one matrix per task or one vector per class is kept for knowledge retention. Extensive experiments on a variety of task sequences show that our method achieves competitive results against state-of-the-art methods, especially in accuracy gain, memory cost, training efficiency, and task-order robustness. Furthermore, to make the non-growing backbone (i.e., a model with limited network capacity) suffice to train on more incoming tasks, a graceful forgetting implementation on previously learned trivial tasks is empirically investigated.

Jiake Ge, Huanchen Zhang, Boyu Shi et al.

The growth in data storage capacity and the increasing demands for high performance have created several challenges for concurrent indexing structures. One promising solution is learned indexes, which use a learning-based approach to fit the distribution of stored data and predictively locate target keys, significantly improving lookup performance. Despite their advantages, prevailing learned indexes exhibit constraints and encounter issues of scalability on multi-core data storage. This paper introduces SALI, the Scalable Adaptive Learned Index framework, which incorporates two strategies aimed at achieving high scalability, improving efficiency, and enhancing the robustness of the learned index. Firstly, a set of node-evolving strategies is defined to enable the learned index to adapt to various workload skews and enhance its concurrency performance in such scenarios. Secondly, a lightweight strategy is proposed to maintain statistical information within the learned index, with the goal of further improving the scalability of the index. Furthermore, to validate their effectiveness, SALI applied the two strategies mentioned above to the learned index structure that utilizes fine-grained write locks, known as LIPP. The experimental results have demonstrated that SALI significantly enhances the insertion throughput with 64 threads by an average of 2.04x compared to the second-best learned index. Furthermore, SALI accomplishes a lookup throughput similar to that of LIPP+.

Kunchi Li, Jun Wan, Shan Yu

Rehearsal approaches in class incremental learning (CIL) suffer from decision boundary overfitting to new classes, which is mainly caused by two factors: insufficiency of old classes data for knowledge distillation and imbalanced data learning between the learned and new classes because of the limited storage memory. In this work, we present a simple but effective approach to tackle these two factors. First, we employ a re-sampling strategy and Mixup K}nowledge D}istillation (Re-MKD) to improve the performances of KD, which would greatly alleviate the overfitting problem. Specifically, we combine mixup and re-sampling strategies to synthesize adequate data used in KD training that are more consistent with the latent distribution between the learned and new classes. Second, we propose a novel incremental influence balance (IIB) method for CIL to tackle the classification of imbalanced data by extending the influence balance method into the CIL setting, which re-weights samples by their influences to create a proper decision boundary. With these two improvements, we present the effective decision boundary learning algorithm (EDBL) which improves the performance of KD and deals with the imbalanced data learning simultaneously. Experiments show that the proposed EDBL achieves state-of-the-art performances on several CIL benchmarks.

Peizhi Wu, Ryan Marcus, Zachary G. Ives

In recent years, \emph{learned cardinality estimation} has emerged as an alternative to traditional query optimization methods: by training machine learning models over observed query performance, learned cardinality estimation techniques can accurately predict query cardinalities and costs -- accounting for skew, correlated predicates, and many other factors that traditional methods struggle to capture. However, query-driven learned cardinality estimators are dependent on sample workloads, requiring vast amounts of labeled queries. Further, we show that state-of-the-art query-driven techniques can make significant and unpredictable errors on queries that are outside the distribution of their training set. We show that these out-of-distribution errors can be mitigated by incorporating the \emph{domain knowledge} used in traditional query optimizers: \emph{constraints} on values and cardinalities (e.g., based on key-foreign-key relationships, range predicates, and more generally on inclusion and functional dependencies). We develop methods for \emph{semi-supervised} query-driven learned query optimization, based on constraints, and we experimentally demonstrate that such techniques can increase a learned query optimizer's accuracy in cardinality estimation, reduce the reliance on massive labeled queries, and improve the robustness of query end-to-end performance.

Zichen Liu, Siyi Li, Wee Sun Lee et al.

MuZero Unplugged presents a promising approach for offline policy learning from logged data. It conducts Monte-Carlo Tree Search (MCTS) with a learned model and leverages Reanalyze algorithm to learn purely from offline data. For good performance, MCTS requires accurate learned models and a large number of simulations, thus costing huge computing time. This paper investigates a few hypotheses where MuZero Unplugged may not work well under the offline RL settings, including 1) learning with limited data coverage; 2) learning from offline data of stochastic environments; 3) improperly parameterized models given the offline data; 4) with a low compute budget. We propose to use a regularized one-step look-ahead approach to tackle the above issues. Instead of planning with the expensive MCTS, we use the learned model to construct an advantage estimation based on a one-step rollout. Policy improvements are towards the direction that maximizes the estimated advantage with regularization of the dataset. We conduct extensive empirical studies with BSuite environments to verify the hypotheses and then run our algorithm on the RL Unplugged Atari benchmark. Experimental results show that our proposed approach achieves stable performance even with an inaccurate learned model. On the large-scale Atari benchmark, the proposed method outperforms MuZero Unplugged by 43%. Most significantly, it uses only 5.6% wall-clock time (i.e., 1 hour) compared to MuZero Unplugged (i.e., 17.8 hours) to achieve a 150% IQM normalized score with the same hardware and software stacks. Our implementation is open-sourced at https://github.com/sail-sg/rosmo.

Artem Moskalev, Anna Sepliarskaia, Ivan Sosnovik et al.

Symmetries built into a neural network have appeared to be very beneficial for a wide range of tasks as it saves the data to learn them. We depart from the position that when symmetries are not built into a model a priori, it is advantageous for robust networks to learn symmetries directly from the data to fit a task function. In this paper, we present a method to extract symmetries learned by a neural network and to evaluate the degree to which a network is invariant to them. With our method, we are able to explicitly retrieve learned invariances in a form of the generators of corresponding Lie-groups without prior knowledge of symmetries in the data. We use the proposed method to study how symmetrical properties depend on a neural network's parameterization and configuration. We found that the ability of a network to learn symmetries generalizes over a range of architectures. However, the quality of learned symmetries depends on the depth and the number of parameters.

Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt et al.

Unsupervised skill learning aims to learn a rich repertoire of behaviors without external supervision, providing artificial agents with the ability to control and influence the environment. However, without appropriate knowledge and exploration, skills may provide control only over a restricted area of the environment, limiting their applicability. Furthermore, it is unclear how to leverage the learned skill behaviors for adapting to downstream tasks in a data-efficient manner. We present Choreographer, a model-based agent that exploits its world model to learn and adapt skills in imagination. Our method decouples the exploration and skill learning processes, being able to discover skills in the latent state space of the model. During adaptation, the agent uses a meta-controller to evaluate and adapt the learned skills efficiently by deploying them in parallel in imagination. Choreographer is able to learn skills both from offline data, and by collecting data simultaneously with an exploration policy. The skills can be used to effectively adapt to downstream tasks, as we show in the URL benchmark, where we outperform previous approaches from both pixels and states inputs. The learned skills also explore the environment thoroughly, finding sparse rewards more frequently, as shown in goal-reaching tasks from the DMC Suite and Meta-World. Website and code: https://skillchoreographer.github.io/

Shenghang Luo, Sunish Kumar Orappanpara Soman, Lutz Lampe et al.

Fiber nonlinearity effects cap achievable rates and ranges in long-haul optical fiber communication links. Conventional nonlinearity compensation methods, such as perturbation theory-based nonlinearity compensation (PB-NLC), attempt to compensate for the nonlinearity by approximating analytical solutions to the signal propagation over optical fibers. However, their practical usability is limited by model mismatch and the immense computational complexity associated with the analytical computation of perturbation triplets and the nonlinearity distortion field. Recently, machine learning techniques have been used to optimise parameters of PB-based approaches, which traditionally have been determined analytically from physical models. It has been claimed in the literature that the learned PB-NLC approaches have improved performance and/or reduced computational complexity over their non-learned counterparts. In this paper, we first revisit the acclaimed benefits of the learned PB-NLC approaches by carefully carrying out a comprehensive performance-complexity analysis utilizing state-of-the-art complexity reduction methods. Interestingly, our results show that least squares-based PB-NLC with clustering quantization has the best performance-complexity trade-off among the learned PB-NLC approaches. Second, we advance the state-of-the-art of learned PB-NLC by proposing and designing a fully learned structure. We apply a bi-directional recurrent neural network for learning perturbation triplets that are alike those obtained from the analytical computation and are used as input features for the neural network to estimate the nonlinearity distortion field. Finally, we demonstrate through numerical simulations that our proposed fully learned approach achieves an improved performance-complexity trade-off compared to the existing learned and non-learned PB-NLC techniques.

Rafael R. S. Guimaraes

Limited datasets and complex nonlinear relationships are among the challenges that may emerge when applying econometrics to macroeconomic problems. This research proposes deep learning as an approach to transfer learning in the former case and to map relationships between variables in the latter case. Although macroeconomists already apply transfer learning when assuming a given a priori distribution in a Bayesian context, estimating a structural VAR with signal restriction and calibrating parameters based on results observed in other models, to name a few examples, advance in a more systematic transfer learning strategy in applied macroeconomics is the innovation we are introducing. We explore the proposed strategy empirically, showing that data from different but related domains, a type of transfer learning, helps identify the business cycle phases when there is no business cycle dating committee and to quick estimate a economic-based output gap. Next, since deep learning methods are a way of learning representations, those that are formed by the composition of multiple non-linear transformations, to yield more abstract representations, we apply deep learning for mapping low-frequency from high-frequency variables. The results obtained show the suitability of deep learning models applied to macroeconomic problems. First, models learned to classify United States business cycles correctly. Then, applying transfer learning, they were able to identify the business cycles of out-of-sample Brazilian and European data. Along the same lines, the models learned to estimate the output gap based on the U.S. data and obtained good performance when faced with Brazilian data. Additionally, deep learning proved adequate for mapping low-frequency variables from high-frequency data to interpolate, distribute, and extrapolate time series by related series.

Andreas Kipf, Dominik Horn, Pascal Pfeil et al.

Learned index structures have been shown to achieve favorable lookup performance and space consumption compared to their traditional counterparts such as B-trees. However, most learned index studies have focused on the primary indexing setting, where the base data is sorted. In this work, we investigate whether learned indexes sustain their advantage in the secondary indexing setting. We introduce Learned Secondary Index (LSI), a first attempt to use learned indexes for indexing unsorted data. LSI works by building a learned index over a permutation vector, which allows binary search to performed on the unsorted base data using random access. We additionally augment LSI with a fingerprint vector to accelerate equality lookups. We show that LSI achieves comparable lookup performance to state-of-the-art secondary indexes while being up to 6x more space efficient.

Sarah Bechtle, Ludovic Righetti, Franziska Meier

Being able to seamlessly generalize across different tasks is fundamental for robots to act in our world. However, learning representations that generalize quickly to new scenarios is still an open research problem in reinforcement learning. In this paper we present a framework to meta-learn the critic for gradient-based policy learning. Concretely, we propose a model-based bi-level optimization algorithm that updates the critics parameters such that the policy that is learned with the updated critic gets closer to solving the meta-training tasks. We illustrate that our algorithm leads to learned critics that resemble the ground truth Q function for a given task. Finally, after meta-training, the learned critic can be used to learn new policies for new unseen task and environment settings via model-free policy gradient optimization, without requiring a model. We present results that show the generalization capabilities of our learned critic to new tasks and dynamics when used to learn a new policy in a new scenario.

Binar Asrining Dhiani, Siti Nurjanah, Narendra Istia Putri et al.

COVID-19 global pandemic increases the usage of vitamin supplement products. However, easy access to purchase and consume the product increases the risk for its misuse. Lack of information and or misinformation available for vitamin supplement product usage leads to its abuse. Teachers' and parents' role in deciding the choice and use of vitamin supplement products for the pupil and children is crucial. Thus, a program was held to provide information about the correct usage of vitamin supplement products for teachers and parents. The program was performed for the teachers and pupil parents of TK Aisyiyah Ledug via online. The attractive audio-visual program materials were delivered via animation video, artistic leaflet, and presentation. The teachers and parents responded positively toward the program. All attendants actively participated, and 100% of attendants agreed that the program was interesting and increased their knowledge on the appropriate usage of vitamin supplement products.

Bagas Narendra Parahita, Dwi Astutik, Ghufronudin Ghufronudin et al.

During distance learning (PJJ), teachers have difficulty developing creativity regarding the online learning process, especially when compiling learning media. Service activities were carried out by the Eduscape Group Research team from the Sebelas Maret University FKIP together with the Sociology MGMP of Karanganyar Regency as an effort to optimize online learning. The learning media provided by Google for Education, especially Google Slides, was chosen to be the main target for the preparation of virtual classes because it has flexibility, ease of use, and is easily accessible by both teachers and students. The method of implementing service activities is carried out in the meeting room of SMA Negeri Karangpandan, Karanganyar Regency, face to face with stringent health protocols. Service activities consist of material presentation, demonstration, mentoring and collection of virtual class results. The result of this activity is that teachers can compose and use and create learning media through various online platforms (google slides, online quizzes, pdf converters, exploration of material content on youtube) to prepare virtual classes.

Imam Safi'i, Agata Iwan Candra, Silvi Rushanti Widodo et al.

The spread of Covid-19 in Indonesia has begun to increase from April 2020, this is because there are still many people who have not implemented the prevention of transmission such as one of them using masks. Observations made at crowded places such as traditional markets found that many people do not use masks due to the scarcity of masks in the market. The methods of making the masks and disinfectant booths aims to help the community, especially in the Kediri region which was affected by the spread of Covid-19. The masks and disinfectant booth products are carried out independently by the Kadiri University in collaboration with the students, lecturers, and alumni of Kadiri University, where the products will be submitted as a form of social service to people in need such as the traditional market in Grogol Village, Kediri Regency. In addition to distributing masks to the public, also given education through socialization the importance of doing a form of prevention of the spread of Covid-19 by always washing hands regularly, keep a distance, and always use a mask.

Kimberly Stachenfeld, Drummond B. Fielding, Dmitrii Kochkov et al.

Turbulence simulation with classical numerical solvers requires high-resolution grids to accurately resolve dynamics. Here we train learned simulators at low spatial and temporal resolutions to capture turbulent dynamics generated at high resolution. We show that our proposed model can simulate turbulent dynamics more accurately than classical numerical solvers at the comparably low resolutions across various scientifically relevant metrics. Our model is trained end-to-end from data and is capable of learning a range of challenging chaotic and turbulent dynamics at low resolution, including trajectories generated by the state-of-the-art Athena++ engine. We show that our simpler, general-purpose architecture outperforms various more specialized, turbulence-specific architectures from the learned turbulence simulation literature. In general, we see that learned simulators yield unstable trajectories; however, we show that tuning training noise and temporal downsampling solves this problem. We also find that while generalization beyond the training distribution is a challenge for learned models, training noise, added loss constraints, and dataset augmentation can help. Broadly, we conclude that our learned simulator outperforms traditional solvers run on coarser grids, and emphasize that simple design choices can offer stability and robust generalization.

Ran Tian, Anjian Li, Masayoshi Tomizuka et al.

Safety assurance is a critical yet challenging aspect when developing self-driving technologies. Hamilton-Jacobi backward-reachability analysis is a formal verification tool for verifying the safety of dynamic systems in the presence of disturbances. However, the standard approach is too conservative to be applied to self-driving applications due to its worst-case assumption on humans' behaviors (i.e., guard against worst-case outcomes). In this work, we integrate a learning-based prediction algorithm and a game-theoretic human behavioral model to online update the conservativeness of backward-reachability analysis. We evaluate our approach using real driving data. The results show that, with reasonable assumptions on human behaviors, our approach can effectively reduce the conservativeness of the standard approach without sacrificing its safety verification ability.